Startup skill router: maps any incoming request to the correct skill using Quick Lookup table and _manifest.json. Loaded automatically at session start. Triggers on: every new request — this is the dispatch layer, not a user-facing skill. NOT for: executing tasks directly — always routes to a domain-specific skill.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.
skills/_manifest.json (lightweight — name + description + triggers for all active skills)skills/skill-master/REFERENCE.md for decision treeDo not load REFERENCE.md or full SKILL.md files unless the manifest and Quick Lookup both miss. Do not improvise. No match anywhere? Ask the owner.
Don't just route reactively. When you detect these patterns, suggest the relevant skill:
PA_LIST.md/path/to/openclaw/.gog/credentials.json (NOT gog CLI)echo "{\"ts\":\"$(date -u +%Y-%m-%dT%H:%M:%SZ)\",\"skill\":\"SKILL_NAME\",\"trigger\":\"TRIGGER\",\"context\":\"CONTEXT\"}" \
>> /path/to/workspace/data/skill-analytics.jsonl
| If the owner says... | Use skill |
|---|---|
| "who is X" / "phone for X" / "email of X" / "address of X" | contact-list |
| "PA of X" / "X's PA" / "JID of X" | contact-list |
| "add contact" / "update contact" | contact-list |
| "schedule a meeting" / "meeting notes" / "action items" | meetings |
| "what's on my calendar" / "morning briefing" | owner-briefing |
| "billing error" / "API out of credits" | billing-monitor |
| "connect calendar" / "connect Gmail" | calendar-setup |
| "set up a new PA" / "onboard agent" | pa-onboarding |
| "personal trainer" / "client check-in" / "workout program" / "fitness clients" | personal-trainer |
| "monday.com" / "create board item" / "track this" | monday-for-agents |
| "backup workspace" / "push to git" / "update openclaw" | pa-maintenance |
| "save this" / "where to save" | storage-router |
| "token usage" / "how much did today cost" | usage-costs |
| "what was discussed in [group]" | heleni-whatsapp |
| "search past messages" / "what did X say" | chat-history-local |
| "security check" / "health check" | self-monitor |
| "PA network status" / "how are PAs doing" | supervisor |
| "how am I doing" / "run eval" | eval |
| "summarize YouTube video" | youtube-watcher |
| "compact memory" / "organize memory" | memory-tiering |
| "reduce token costs" / "optimize costs" | openclaw-token-optimizer |
| "CRM update" / "pre-meeting brief" | personal-crm |
| "research X" / "find out about X" | research-synthesizer |
| "should I reply?" | silence-strategy |
| "transcribe voice message" | whatsapp-voice |
| "deep recall" / "did we discuss" / "what happened with" | deep-recall |
| "$ownership" / "execute with ownership" | ownership |
| "$devprocess" / "build this properly" / "use coding agent workflow" | devprocess |
| "reflect on this" / "fix how you operate" / "turn this into a durable fix" | self-reflection |
| "this should be a skill" / "save this as a skill" | auto-skill-creator |
| "knowledge graph" / "graphify" / "wiki compile" | knowledge-graph |
| "publish this" / "share this as a webpage" | publish-to-mdpage |
| "connect to X API" / "OAuth" / "external service integration" | api-gateway |
| "LinkedIn post" / "personal brand" / "Substack draft" | self-brand |
| Said "I'll send" / "I'll report" in a reply | commitment-tracker |
| "I made a mistake" / "owner corrected me" | self-learning |
Storage rule: Before saving content, run
storage-router. Research -> monday.com. State/config -> local.
Privacy review (before push): Scan for internal names, phone numbers, JIDs, board IDs. Replace with placeholders.
Skill count: 43 active. Above 30, keep routing tight and prefer the most specific skill first.
아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.
로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.
아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.
AI Personal Assistant network skill. Use when: contacting another PA, coordinating with peer agents, scheduling meetings between owners, broadcasting messages, looking up contacts from the local PA directory, or performing any cross-PA task. Reads contact data from data/pa-directory.json in the workspace. Does NOT contain hardcoded contact data — each PA maintains their own directory file.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
AI Personal Assistant network skill for multi-agent PA coordination. Use when: contacting another PA, coordinating with peer agents, scheduling meetings between owners, broadcasting messages to PA groups, or looking up contacts from the local PA directory. Reads contact data from data/pa-directory.json in the workspace.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Route and execute inter-PA coordination tasks in the OpenClaw multi-agent PA network. Triggers when: contacting another PA, passing a message between owners, broadcasting to a PA group, handling group lead/silence rules, or adding a new PA to the directory. NOT for: contact lookups (use contact-list skill), calendar invites (use meetings skill), or billing issues (use billing-monitor skill).
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
OpenClaw API gateway proxy for authenticated SaaS calls (100+ services in references/SERVICES.md). Use ONLY when making an HTTP request to a third-party service that requires the gateway's stored credentials. NOT for direct API calls with bearer tokens already in scope, NOT for monday.com (use monday-for-agents), NOT for WhatsApp (use heleni-whatsapp). Triggers: "call the X API", "fetch from <service>", "send to Slack via gateway", "use the gateway for".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Automatically creates new skills from complex problem-solving sessions. Triggers at the end of multi-step tasks that required novel approaches, debugging sessions, or workflow creation. Use when: a task took 3+ tool calls, involved a non-obvious solution, or established a pattern likely to recur. Also triggers on: "create a skill from this", "save this as a skill", "this should be a skill".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Monitor for API billing errors and alert the owner and admin immediately. Use when: an API billing error is detected, a peer PA reports a billing error, or during routine health checks. Handles detection, notification, and fallback model switching. Model-agnostic: works with any LLM provider (Anthropic, OpenAI, Google, etc.).
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.